summary

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, non-destructive behavior; the description adds the concrete content returned (steps, counts, cost, latency), which is useful context beyond the annotations. It does not detail edge cases or how metrics are computed, but that is acceptable given annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one short, front-loaded sentence that lists what the summary contains. There is no filler or redundant information; every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-argument, read-only summary tool with annotations and an output schema, the description covers the key categories of information. It does not over-explain, and the output schema can handle detailed return values. The phrase 'so far' provides the temporal scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. There are no parameters requiring additional explanation, and the description complies with that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides a session summary with specific data points (steps, counts, cost, latency), and the phrase 'session so far' distinguishes it from page-specific sibling tools. It lacks an explicit verb like 'Returns' or 'Shows', but the intent is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no direct guidance on when to use this tool versus siblings such as page_state or perf_metrics. The only hint is 'session so far,' which implies but does not explicitly state that this is for accumulated session data rather than current page state.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.